Mystery: examining a crime scene

Bad Writing Habits

Detects common prose quality anti-patterns in AI-generated creative writing, including passive voice, past progressive overuse, weak dialogue tags, filter words, purple prose, cliches, AI-ism words/adverbs/names, and more.

Creative Writing Hallucination

Performance Score Distribution (Top 20)

Click a model name to view its detail page.

	Score
GPT-5.4 (Reasoning)	92%
GPT-5.4	92%
GPT-5.6 Luna (Reasoning)	91%
GPT-5.6 Terra (Reasoning)	91%
GPT-5.5	91%
GPT-5.4 (Reasoning, Low)	91%
GPT-5.5 (Reasoning, Low)	90%
GPT-5.6 Terra	90%
GPT-5.6 Sol (Reasoning)	90%
GPT-5.5 (Reasoning)	90%
GPT-5.6 Sol	89%
GPT-5.4 Mini	89%
GPT-5.4 Mini (Reasoning)	89%
GPT-5.6 Luna	88%
GPT-5.4 Mini (Reasoning, Low)	87%
Qwen3.6 Max Preview	87%
Muse Spark 1.1 (Reasoning, Medium)	87%
Gemini 3.5 Flash Lite (Reasoning, Minimal)	87%
Claude Opus 5 (Reasoning)	86%
Grok 4.5 (Reasoning, High)	86%

	Score	Cost	Time
GPT-5.6 Luna (Reasoning)	91%	$0.017	17.8s
Gemini 3.5 Flash Lite (Reasoning, Minimal)	87%	$0.0040	8.2s
Qwen 3.6 35B	86%	$0.0090	58.9s
Gemini 3.5 Flash Lite (Reasoning)	85%	$0.0037	7.5s
GPT-5.6 Luna	88%	$0.016	15.9s
GPT-5.4 Mini (Reasoning, Low)	87%	$0.016	18.8s
Muse Spark 1.1 (Reasoning, Medium)	87%	$0.013	22.7s
GPT-5.4 Mini	89%	$0.017	19.5s
Qwen 3.6 Flash	86%	$0.0090	36.8s
Grok 4.3	84%	$0.0053	27.4s
Mistral Small 4 (Reasoning)	83%	$0.0022	30.7s
GPT-5.6 Terra (Reasoning)	91%	$0.046	39.7s
Qwen 3 32B	83%	$0.0012	39.7s
DeepSeek V4 Flash	83%	$0.0005	26.7s
GPT-5.4 Mini (Reasoning)	89%	$0.031	37.4s
GPT-5.4 Nano	80%	$0.0057	20.4s
Mistral Large 3	82%	$0.0026	28.4s
Muse Spark 1.1 (Reasoning, Minimal)	83%	$0.012	19.8s
Grok 4.5 (Reasoning, Low)	85%	$0.020	58.7s
Mistral NeMO	81%	$0.0003	11.1s

	Score	Cost	Speed	Stability
GPT-5.6 Luna (Reasoning)	91%	$0.017	17.8s	87%
Gemini 3.5 Flash Lite (Reasoning, Minimal)	87%	$0.0040	8.2s	84%
GPT-5.6 Terra (Reasoning)	91%	$0.046	39.7s	88%
GPT-5.6 Luna	88%	$0.016	15.9s	84%
Muse Spark 1.1 (Reasoning, Medium)	87%	$0.013	22.7s	84%
GPT-5.4 Mini (Reasoning, Low)	87%	$0.016	18.8s	84%
GPT-5.6 Terra	90%	$0.055	43.2s	88%
GPT-5.4 Mini	89%	$0.017	19.5s	80%
GPT-5.4 Mini (Reasoning)	89%	$0.031	37.4s	84%
Gemini 3.5 Flash Lite (Reasoning)	85%	$0.0037	7.5s	80%
GPT-5.4	92%	$0.057	1.6m	88%
Qwen 3.6 Flash	86%	$0.0090	36.8s	80%
Qwen 3.6 35B	86%	$0.0090	58.9s	81%
Grok 4.3	84%	$0.0053	27.4s	79%
Qwen 3 32B	83%	$0.0012	39.7s	80%
GPT-5.4 (Reasoning, Low)	91%	$0.060	1.6m	87%
Grok 4.5 (Reasoning, Low)	85%	$0.020	58.7s	82%
Mistral Small 4 (Reasoning)	83%	$0.0022	30.7s	78%
Claude Sonnet 4.5	85%	$0.029	35.7s	81%
Grok 4.5 (Reasoning, High)	86%	$0.023	1.3m	81%

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
35	GPT-5.4 (Reasoning)	$0.100	3.1m	91%	94	93	93	91	91	92%
11	GPT-5.4	$0.057	1.6m	88%	95	92	92	90	89	92%
1	GPT-5.6 Luna (Reasoning)	$0.017	17.8s	87%	94	91	90	90	89	91%
3	GPT-5.6 Terra (Reasoning)	$0.046	39.7s	88%	92	92	91	91	88	91%
113	GPT-5.5	$0.166	1.8m	85%	95	90	90	90	88	91%
16	GPT-5.4 (Reasoning, Low)	$0.060	1.6m	87%	93	93	92	89	85	91%
106	GPT-5.5 (Reasoning, Low)	$0.156	2.1m	86%	93	92	90	89	88	90%
7	GPT-5.6 Terra	$0.055	43.2s	88%	91	91	91	90	87	90%
39	GPT-5.6 Sol (Reasoning)	$0.113	1.2m	88%	92	91	90	89	88	90%
117	GPT-5.5 (Reasoning)	$0.164	2.1m	87%	91	91	89	89	88	90%
52	GPT-5.6 Sol	$0.120	1.3m	88%	90	90	90	89	87	89%
8	GPT-5.4 Mini	$0.017	19.5s	80%	95	90	87	86	85	89%
9	GPT-5.4 Mini (Reasoning)	$0.031	37.4s	84%	93	89	88	87	86	89%
4	GPT-5.6 Luna	$0.016	15.9s	84%	91	90	87	86	86	88%
6	GPT-5.4 Mini (Reasoning, Low)	$0.016	18.8s	84%	89	88	87	87	84	87%
46	Qwen3.6 Max Preview	$0.046	3.4m	85%	89	88	87	86	85	87%
5	Muse Spark 1.1 (Reasoning, Medium)	$0.013	22.7s	84%	89	87	87	86	85	87%
2	Gemini 3.5 Flash Lite (Reasoning, Minimal)	$0.0040	8.2s	84%	90	87	87	85	84	87%
90	Claude Opus 5 (Reasoning)	$0.105	1.2m	80%	91	90	86	83	82	86%
20	Grok 4.5 (Reasoning, High)	$0.023	1.3m	81%	91	88	86	85	83	86%
47	Claude Opus 5	$0.082	57.9s	83%	89	86	86	85	85	86%
13	Qwen 3.6 35B	$0.0090	58.9s	81%	90	88	88	87	78	86%
65	MoonshotAI: Kimi K3 (Reasoning, High)	$0.045	1.9m	78%	92	86	84	83	83	86%
12	Qwen 3.6 Flash	$0.0090	36.8s	80%	89	89	86	84	80	86%
40	Claude Opus 4.7 (Reasoning)	$0.071	34.5s	82%	89	86	86	84	83	86%
104	Claude Opus 5 (Reasoning, Low)	$0.100	1.1m	78%	92	87	84	82	81	85%
86	Qwen3.7 Max	$0.059	2.3m	79%	89	89	84	82	82	85%
92	GPT-5	$0.073	3.0m	83%	87	87	86	83	83	85%
49	GPT-5.1	$0.063	1.5m	83%	86	86	85	85	83	85%
17	Grok 4.5 (Reasoning, Low)	$0.020	58.7s	82%	87	86	86	83	81	85%
156	MoonshotAI: Kimi K2.6	$0.043	8.2m	79%	90	86	85	82	81	85%
19	Claude Sonnet 4.5	$0.029	35.7s	81%	87	85	84	84	82	85%
10	Gemini 3.5 Flash Lite (Reasoning)	$0.0037	7.5s	80%	88	86	85	83	81	85%
61	Claude Opus 4.8 (Reasoning, Low)	$0.068	47.0s	80%	88	86	84	82	82	84%
14	Grok 4.3	$0.0053	27.4s	79%	88	87	85	83	79	84%
51	Qwen 3.5 397B A17B	$0.030	2.3m	80%	86	85	85	85	79	84%
18	Mistral Small 4 (Reasoning)	$0.0022	30.7s	78%	87	86	83	82	78	83%
15	Qwen 3 32B	$0.0012	39.7s	80%	85	84	83	83	80	83%
62	Qwen 3.6 27B	$0.016	1.5m	74%	91	82	81	81	80	83%
149	Claude Opus 4	$0.147	1.0m	79%	85	85	84	83	77	83%
63	Claude Opus 4.7	$0.064	34.5s	80%	85	84	84	83	79	83%
55	MiniMax M3	$0.0031	2.0m	75%	91	84	83	79	77	83%
23	DeepSeek V4 Flash	$0.0005	26.7s	75%	90	83	82	80	78	83%
21	Muse Spark 1.1 (Reasoning, Minimal)	$0.012	19.8s	78%	85	85	83	80	79	83%
22	Mistral Large 3	$0.0026	28.4s	76%	88	82	81	81	80	82%
143	Gemini 3.1 Pro (Preview)	$0.083	1.5m	71%	91	88	80	78	75	82%
36	Hermes 3 405B	$0.0020	59.2s	74%	88	86	82	78	76	82%
105	MoonshotAI: Kimi K3 (Reasoning, Low)	$0.028	1.2m	67%	90	90	77	77	75	82%
66	Grok 4.20 (Reasoning)	$0.016	1.4m	75%	88	86	81	79	76	82%
30	MiniMax M2.5	$0.0030	1.0m	76%	87	83	83	81	75	82%
24	Claude Sonnet 5	$0.024	36.0s	81%	83	83	83	81	81	82%
32	Aion 3.0 Mini	$0.0045	1.1m	77%	86	82	81	81	78	82%
28	Grok 4.20	$0.0078	40.7s	77%	85	84	81	81	78	82%
58	Claude Sonnet 4.6	$0.031	48.5s	77%	87	83	83	77	77	82%
42	Aion 3.0	$0.018	57.6s	78%	85	83	82	81	78	81%
94	Grok 4.3 (Reasoning)	$0.016	2.6m	73%	87	85	81	78	76	81%
33	Qwen3 235B A22B Instruct 2507	$0.0011	1.1m	77%	85	84	81	79	78	81%
72	Z.AI GLM 5.1	$0.012	1.3m	73%	89	85	82	77	73	81%
34	Qwen 3.5 Flash	$0.0019	36.5s	75%	88	81	80	79	78	81%
57	Mistral Large 2	$0.011	28.7s	72%	89	84	79	78	76	81%
29	Writer: Palmyra X5	$0.011	24.2s	77%	83	83	80	80	79	81%
89	Claude Opus 4.8 (Reasoning)	$0.067	45.2s	79%	83	82	81	81	78	81%
31	o4 Mini	$0.014	22.3s	77%	83	83	82	79	76	81%
27	Mistral NeMO	$0.0003	11.1s	75%	87	80	80	80	77	81%
138	Claude Opus 4.6 (Reasoning)	$0.086	1.4m	76%	84	84	81	79	76	81%
56	Claude Sonnet 5 (Reasoning, Low)	$0.025	35.6s	76%	85	82	81	80	75	81%
25	GPT-5.4 Nano (Reasoning, Low)	$0.0055	20.4s	77%	84	81	81	79	77	81%
26	GPT-5.4 Nano	$0.0057	20.4s	77%	83	83	82	79	75	80%
68	o4 Mini High	$0.023	38.2s	74%	86	82	80	78	76	80%
82	Qwen 3.5 Plus (2026-04-20)	$0.015	1.5m	74%	85	83	80	79	74	80%
64	Z.AI GLM 5 Turbo	$0.0081	37.9s	72%	87	83	80	77	74	80%
43	GPT-5 Mini	$0.0099	40.3s	76%	84	79	79	79	79	80%
60	Gemini 3.5 Flash (Reasoning, Minimal)	$0.019	12.7s	74%	84	83	80	78	73	80%
122	GPT-5.2	$0.060	1.6m	75%	84	80	79	78	78	80%
45	DeepSeek V3 (2025-03-24)	$0.0016	33.7s	74%	83	83	80	80	72	80%
78	GPT-4.1	$0.018	40.9s	73%	84	83	79	76	75	79%
54	Gemma 3 27B	$0.0007	45.4s	73%	85	83	80	77	73	79%
38	Mistral Small 4	$0.0011	18.0s	75%	84	81	80	78	74	79%
73	DeepSeek V4 Pro (Reasoning)	$0.0035	1.8m	76%	83	81	81	76	75	79%
79	Ministral 3 8B	$0.0023	1.5m	73%	86	81	80	75	75	79%
59	Gemini 3.1 Flash Lite (Preview)	$0.0026	8.1s	71%	86	82	77	76	76	79%
37	Ministral 3 14B	$0.0005	12.5s	75%	82	81	80	79	74	79%
101	Gemini 2.5 Pro	$0.040	41.1s	72%	84	82	78	77	74	79%
44	Mistral Medium 3.1	$0.0045	34.0s	76%	82	81	81	77	74	79%
77	Qwen 3.5 9B	$0.0008	1.2m	72%	85	80	78	75	75	79%
80	Z.AI GLM 5.2 (Reasoning, High)	$0.011	1.1m	73%	84	80	79	77	75	79%
48	DeepSeek V4 Flash (Reasoning)	$0.0008	38.0s	75%	82	82	81	77	73	79%
53	ByteDance Seed 1.6 Flash	$0.0014	30.1s	73%	84	80	78	77	75	79%
67	DeepSeek-V2 Chat	$0.0016	36.9s	72%	84	81	80	79	70	79%
41	Gemma 3 12B	$0.0004	37.1s	76%	81	81	80	76	75	79%
97	Cohere Command R+ (Aug. 2024)	$0.016	1.3m	71%	84	84	79	75	71	79%
50	GPT-5.4 Nano (Reasoning)	$0.0060	22.2s	75%	82	80	79	77	74	78%
75	Gemini 2.5 Flash (Reasoning)	$0.013	24.5s	72%	83	81	80	79	69	78%
74	Qwen 3.5 122B	$0.013	36.8s	74%	83	81	81	74	72	78%
136	Claude Opus 4.5	$0.067	56.1s	73%	82	80	77	77	75	78%
129	ByteDance Seed 2.0 Lite	$0.012	2.1m	68%	89	80	79	72	70	78%
81	MiniMax M2.7	$0.0033	1.3m	74%	82	80	78	76	75	78%
142	Claude Opus 4.6	$0.077	1.3m	75%	81	80	78	76	74	78%
85	Z.AI GLM 5	$0.0079	1.1m	73%	83	77	77	77	77	78%
76	Gemini 3.1 Flash Lite	$0.0026	9.6s	70%	82	82	77	76	70	78%
91	Gemini 3.6 Flash (Reasoning)	$0.035	30.6s	74%	80	79	77	76	75	77%
69	Gemini 2.5 Flash	$0.0057	11.6s	73%	81	78	76	76	74	77%
140	Thinking Machines Inkling	$0.0081	2.9m	69%	86	77	76	74	73	77%
99	DeepSeek V4 Pro	$0.0044	1.4m	71%	83	79	77	76	71	77%
71	Xiaomi MIMO v2.5	$0.0057	34.4s	74%	79	78	77	77	73	77%
70	Gemini 2.5 Flash Lite	$0.0009	11.8s	72%	80	79	77	76	72	77%
161	Thinking Machines Inkling (Reasoning)	$0.022	7.6m	70%	81	79	74	74	74	76%
96	Laguna XS 2.1	$0.0003	20.7s	67%	85	80	75	72	70	76%
111	Qwen 3.5 27B	$0.0097	57.2s	69%	84	77	75	73	72	76%
116	Qwen 3.5 35B	$0.011	37.9s	66%	86	77	74	73	72	76%
153	ByteDance Seed 2.0 Mini	$0.0049	5.4m	75%	77	77	76	76	75	76%
87	Llama 3.1 70B	$0.0007	33.1s	71%	80	78	75	74	74	76%
88	GPT-4o Mini (temp=1)	$0.0011	25.2s	71%	81	75	75	75	74	76%
150	DeepSeek V3.2	$0.0011	3.3m	67%	84	78	75	72	70	76%
84	Gemini 2.5 Flash Lite (Reasoning)	$0.0025	26.5s	72%	79	78	75	74	74	76%
132	MoonshotAI: Kimi K2.5	$0.012	1.0m	66%	86	77	76	70	68	75%
144	Claude Sonnet 4.6 (Reasoning)	$0.043	1.1m	70%	81	77	77	74	67	75%
134	Hermes 3 70B	$0.0006	31.1s	62%	84	82	71	71	69	75%
137	Z.AI GLM 4.7	$0.0098	1.9m	69%	80	77	74	73	72	75%
148	ByteDance Seed 1.6	$0.016	3.1m	72%	78	75	74	74	74	75%
110	Claude Sonnet 5 (Reasoning)	$0.023	34.5s	72%	78	78	77	74	68	75%
125	Aion 2.0	$0.0051	1.2m	68%	81	79	74	72	69	75%
83	GPT-4o Mini (temp=0)	$0.0010	24.7s	73%	77	76	75	74	73	75%
93	DeepSeek V3 (2024-12-26)	$0.0017	40.7s	71%	78	77	75	74	70	75%
130	Gemini 3.5 Flash (Reasoning)	$0.041	24.4s	70%	79	76	74	74	71	75%
115	Ministral 3B	$0.0001	1.1m	68%	82	76	73	72	71	75%
107	Ministral 3 3B	$0.0015	55.5s	70%	80	77	75	73	70	75%
95	Qwen 2.5 72B	$0.0006	27.7s	70%	79	79	75	71	71	75%
102	Xiaomi MIMO v2.5 Pro	$0.0080	52.9s	72%	77	76	75	74	71	75%
124	Cydonia 24B V4.1	$0.0009	34.2s	65%	82	80	73	72	66	75%
135	Z.AI GLM 4.7 Flash	$0.0020	1.3m	66%	84	73	73	72	70	75%
109	Z.AI GLM 4.5 Air	$0.0018	34.5s	69%	78	78	75	73	67	74%
145	Claude Sonnet 4	$0.028	43.4s	66%	79	79	74	73	65	74%
126	DeepSeek V3.1	$0.0014	1.7m	70%	78	76	75	71	70	74%
119	Laguna S 2.1	$0.0004	29.8s	66%	82	75	73	72	68	74%
100	GPT-4o, Aug. 6th (temp=0)	$0.016	29.9s	73%	75	74	74	74	73	74%
139	Z.AI GLM 4.6	$0.0062	1.4m	67%	78	77	72	72	70	74%
118	GPT-4o, Aug. 6th (temp=1)	$0.016	36.9s	70%	79	75	75	71	69	74%
103	GPT-4.1 Mini	$0.0027	16.6s	69%	78	76	74	70	70	74%
128	Claude Haiku 4.5	$0.0093	20.2s	66%	80	79	73	69	67	74%
123	Gemini 3.6 Flash (Reasoning, Minimal)	$0.017	16.3s	68%	77	77	73	72	68	74%
98	Gemma 3 4B	$0.0002	18.9s	70%	76	75	74	72	70	73%
112	WizardLM 2 8x22b	$0.0016	24.6s	69%	78	77	76	69	66	73%
127	Qwen 3.5 Plus (2026-02-15)	$0.0051	25.8s	67%	79	74	72	71	70	73%
114	Ministral 8B	$0.0002	9.9s	67%	80	77	76	68	63	73%
131	Gemini 3.1 Flash Lite (Reasoning)	$0.0026	22.1s	65%	83	77	77	68	60	73%
133	Z.AI GLM 4.5	$0.0045	37.2s	67%	79	73	73	72	66	73%
108	GPT-4.1 Nano	$0.0006	10.5s	70%	75	74	74	71	68	72%
120	Gemini 3 Flash (Preview)	$0.0067	17.5s	69%	74	72	72	71	68	72%
121	Arcee AI: Trinity Mini	$0.0003	9.0s	67%	77	75	73	68	66	72%
147	Gemma 4 31B (Reasoning)	$0.0012	1.7m	68%	74	74	70	70	70	72%
141	Gemini 3 Flash (Preview, Reasoning)	$0.010	25.1s	66%	78	73	72	68	66	72%
146	Gemma 4 31B	$0.0008	1.5m	67%	74	73	71	69	68	71%
152	Nemotron 3 Super	$0.0000	1.3m	65%	74	70	68	68	67	69%
155	Gemma 4 26B (Reasoning)	$0.0013	2.2m	66%	72	71	69	67	66	69%
154	Gemma 4 26B	$0.0007	41.6s	63%	77	72	71	66	60	69%
158	Mistral Small 3.2 24B	$0.0034	1.8m	62%	77	70	69	68	60	69%
151	Inception Mercury 2	$0.0031	7.9s	65%	68	68	67	66	65	67%
159	GPT-5 Nano	$0.0042	1.4m	63%	71	67	66	65	64	67%
157	GPT-OSS 120B	$0.0026	54.7s	63%	70	67	66	65	64	67%
160	Nemotron 3 Nano	$0.0007	42.1s	56%	77	69	63	63	61	67%
79.39%

Median	Evaluator	Top 3	Flop 3
91.8%	"Not X but Y" pattern overuse	100Gemini 3.5 Flash Lite (Reasoning, Minimal) 100Qwen 3.6 27B 100Muse Spark 1.1 (Reasoning, Medium)	0Thinking Machines Inkling 2GPT-5 Nano 23Thinking Machines Inkling (Reasoning)
50.0%	Adverb-first sentence starts	95Writer: Palmyra X5 93Ministral 3 14B 91GPT-5.5 (Reasoning)	0Qwen 2.5 72B 0Hermes 3 70B 0GPT-4o Mini (temp=0)
96.0%	Adverbs in dialogue tags	100Cohere Command R+ (Aug. 2024) 100GPT-5.5 (Reasoning, Low) 100Gemma 4 31B (Reasoning)	20GPT-4.1 Nano 31GPT-4.1 Mini 38Claude Haiku 4.5
88.0%	AI-ism adverb frequency	98ByteDance Seed 1.6 Flash 98ByteDance Seed 2.0 Lite 98DeepSeek V4 Flash	60Gemma 3 4B 68GPT-4.1 Nano 68GPT-4.1 Mini
100.0%	AI-ism character names	100Qwen 3.5 35B 100Ministral 8B 100Arcee AI: Trinity Mini	80DeepSeek V4 Flash 80Mistral NeMO 80DeepSeek V4 Pro
100.0%	AI-ism location names	100GPT-5.4 (Reasoning, Low) 100Qwen3 235B A22B Instruct 2507 100Claude Opus 5	96Muse Spark 1.1 (Reasoning, Minimal) 96Claude Haiku 4.5
56.0%	AI-ism word frequency	91Claude Sonnet 5 (Reasoning, Low) 91Claude Opus 5 86MoonshotAI: Kimi K3 (Reasoning, Low)	3GPT-4o Mini (temp=0) 8GPT-4o, Aug. 6th (temp=1) 11GPT-4o, Aug. 6th (temp=0)
100.0%	Cliché density	100Arcee AI: Trinity Mini 100ByteDance Seed 2.0 Mini 100DeepSeek V3 (2025-03-24)	33Mistral Small 3.2 24B 53GPT-OSS 120B 53Inception Mercury 2
88.4%	Dialogue tag variety (said vs. fancy)	100GPT-5.6 Terra (Reasoning) 100GPT-5.6 Sol (Reasoning) 100Claude Opus 4.6	0Qwen 3.5 Plus (2026-02-15) 3Gemma 4 31B 13Gemma 4 26B
11.9%	Em-dash & semicolon overuse	100Qwen3.7 Max 100GPT-5.6 Luna 100GPT-5.6 Terra	0DeepSeek V3 (2024-12-26) 0GPT-5.4 Nano (Reasoning, Low) 0Gemma 4 26B (Reasoning)
100.0%	Emotion telling (show vs. tell)	100DeepSeek-V2 Chat 100Gemma 4 26B (Reasoning) 100Qwen 3.5 Plus (2026-02-15)	88Mistral Small 3.2 24B 90GPT-4o Mini (temp=0) 93Hermes 3 70B
94.1%	Filter word density	100Ministral 3 14B 100GPT-5.4 Mini 100GPT-4.1 Mini	8Inception Mercury 2 9Nemotron 3 Nano 27GPT-OSS 120B
100.0%	Gibberish response detection	100MoonshotAI: Kimi K3 (Reasoning, High) 100Gemma 3 4B 100Gemini 3 Flash (Preview, Reasoning)	98Qwen 2.5 72B 99MiniMax M2.5 99Qwen 3 32B
100.0%	Markdown formatting overuse	100Hermes 3 405B 100DeepSeek V3.2 100o4 Mini	93ByteDance Seed 1.6 Flash
100.0%	Missing dialogue indicators (quotation marks)	100Laguna XS 2.1 100GPT-5.6 Terra 100Claude Opus 5	0Qwen3.6 Max Preview 20Qwen 3.5 397B A17B 23Gemini 3.5 Flash Lite (Reasoning, Minimal)
50.0%	Name drop frequency	99Claude Opus 5 (Reasoning, Low) 96Claude Opus 4.8 (Reasoning) 95Claude Sonnet 5 (Reasoning)	0GPT-5.5 (Reasoning) 1Z.AI GLM 4.5 3GPT-5.5 (Reasoning, Low)
79.8%	Narrator intent-glossing	100Qwen 3.5 Flash 100ByteDance Seed 1.6 Flash 100GPT-5.5 (Reasoning, Low)	11GPT-5 Nano 17Nemotron 3 Nano 20GPT-4o, Aug. 6th (temp=1)
100.0%	Overuse of "that" (subordinate clause padding)	100o4 Mini 100DeepSeek V3 (2025-03-24) 100MoonshotAI: Kimi K2.5	70Claude Sonnet 5 (Reasoning) 74Mistral Small 3.2 24B 74Hermes 3 70B
100.0%	Paragraph length variance	100Mistral Small 4 100Claude Opus 4.6 100Gemini 3.5 Flash (Reasoning)	53GPT-5 Nano 65ByteDance Seed 2.0 Lite 67Nemotron 3 Nano
88.9%	Passive voice overuse	99Hermes 3 405B 99DeepSeek V3 (2025-03-24) 98o4 Mini High	65ByteDance Seed 2.0 Mini 70Nemotron 3 Super 76Nemotron 3 Nano
80.0%	Past progressive (was/were + -ing) overuse	100GPT-5.4 (Reasoning, Low) 100MoonshotAI: Kimi K2.6 100GPT-5 Mini	0Gemini 3 Flash (Preview) 10Gemma 4 31B (Reasoning) 12Z.AI GLM 4.6
94.1%	Pronoun-first sentence starts	100Claude Sonnet 4.5 100GPT-5.4 Mini (Reasoning) 100GPT-5.4 (Reasoning)	35Gemma 4 26B 36Gemini 3.1 Flash Lite 40Qwen 3.5 27B
97.6%	Purple prose (modifier overload)	100Mistral Large 3 100o4 Mini High 100Mistral Small 3.2 24B	84GPT-4.1 Nano 86Gemma 3 4B 88ByteDance Seed 2.0 Mini
100.0%	Repeated phrase echo	100GPT-4o, Aug. 6th (temp=0) 100Qwen 3.5 35B 100Grok 4.5 (Reasoning, Low)	—
100.0%	Sentence length variance	100GPT-4o, Aug. 6th (temp=0) 100Qwen 3.6 35B 100Claude Opus 4	99Cohere Command R+ (Aug. 2024) 99Hermes 3 70B 100Mistral Small 3.2 24B
57.4%	Sentence opener variety	97Claude Sonnet 5 (Reasoning) 92Claude Sonnet 5 91GPT-4o Mini (temp=1)	34GPT-5 Nano 37Inception Mercury 2 39Qwen 3.5 35B
47.7%	Subject-first sentence starts	100Gemini 3.5 Flash Lite (Reasoning) 96Gemini 3.5 Flash Lite (Reasoning, Minimal) 93GPT-5.4	1Inception Mercury 2 3GPT-OSS 120B 7Arcee AI: Trinity Mini
40.0%	Subordinate conjunction sentence starts	100Gemini 3.1 Flash Lite (Preview) 91Gemini 3.1 Flash Lite 91Qwen 3.6 35B	0Claude Opus 5 0Claude Sonnet 4 0GPT-4.1 Mini
64.6%	Technical jargon density	100GPT-5.5 (Reasoning, Low) 100GPT-5.6 Sol (Reasoning) 100GPT-5.6 Sol	0ByteDance Seed 2.0 Lite 0GPT-5 Nano 0Nemotron 3 Nano
58.9%	Useless dialogue additions	100GPT-5.6 Sol (Reasoning) 100GPT-5.4 (Reasoning, Low) 100Qwen3.6 Max Preview	0Gemma 3 4B 0Ministral 3 3B 0Z.AI GLM 4.6

Bad Writing Habits

Mystery: examining a crime scene

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)